Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization". Do NOT use for accessibility (use web-accessibility), performance (use core-web-vitals), or comprehensive site audits covering multiple areas (use web-quality-audit).
72
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(quality)/seo/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description with strong trigger terms, explicit 'Use when' and 'Do NOT use' clauses, and clear boundaries against related skills. Its main weakness is that the core capability statement is somewhat high-level—it could benefit from listing more specific concrete actions the skill performs beyond what's implied in the trigger terms.
Suggestions
Expand the opening capability statement to list more specific actions, e.g., 'Analyzes and improves meta tags, heading structure, structured data markup, sitemaps, canonical URLs, and keyword optimization for search engine visibility and ranking.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (SEO) and mentions some actions like 'fix meta tags', 'add structured data', 'sitemap optimization', but the primary capability statement 'Optimize for search engine visibility and ranking' is fairly high-level and doesn't list multiple concrete actions the skill performs. | 2 / 3 |
Completeness | Clearly answers both 'what' (optimize for search engine visibility and ranking) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Additionally includes helpful 'Do NOT use' guidance to disambiguate from related skills. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'improve SEO', 'optimize for search', 'fix meta tags', 'add structured data', 'sitemap optimization', 'search engine optimization'. These are phrases users would naturally say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive due to explicit boundary-setting with 'Do NOT use' clauses that differentiate it from web-accessibility, core-web-vitals, and web-quality-audit skills. The SEO-specific trigger terms create a clear niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with concrete, well-formatted code examples and clear good/bad comparisons across all SEO topics. However, it is far too verbose for a SKILL.md—it reads more like a comprehensive SEO reference manual than a concise skill file, with extensive inline content that should be split into separate reference files. It also lacks a clear step-by-step workflow for actually performing an SEO optimization task.
Suggestions
Split the structured data examples (Organization, Article, Product, FAQ, Breadcrumbs) into a separate STRUCTURED-DATA.md reference file and link to it from the main skill.
Move the mobile SEO, international SEO, and detailed guidelines sections into separate reference files, keeping only a brief summary with links in SKILL.md.
Add an explicit workflow section at the top: 'Run Lighthouse SEO audit → Fix critical issues → Validate with Rich Results Test → Re-run audit to confirm improvements' with clear validation checkpoints.
Remove obvious guidelines Claude already knows (e.g., 'Use HTTPS always', 'Lowercase only', 'Use hyphens not underscores') to significantly reduce token count.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose at ~400+ lines. The SEO fundamentals table explaining ranking factors, extensive guidelines lists (title tag guidelines, meta description guidelines, URL guidelines, etc.), and basic concepts like 'use HTTPS' and 'use hyphens not underscores' are things Claude already knows. The structured data section alone has 5 full JSON-LD examples that could be condensed significantly or referenced externally. | 1 / 3 |
Actionability | The skill provides fully concrete, copy-paste ready code examples throughout: complete robots.txt, XML sitemap, HTML meta tags, JSON-LD structured data schemas, CSS examples for mobile. Every section has specific, executable examples with clear good/bad comparisons. | 3 / 3 |
Workflow Clarity | The audit checklist at the end provides a prioritized sequence (Critical → High → Medium → Ongoing), but there's no explicit workflow for performing an SEO optimization task. No validation checkpoints or feedback loops are defined—e.g., 'run Lighthouse, fix issues, re-run to verify.' The structured data section mentions validation tools but doesn't integrate them into a workflow. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with everything inline. The 5 full JSON-LD examples, mobile SEO section, international SEO section, and detailed guidelines could all be split into separate reference files. The only external references are to sibling skills and external URLs—no content is offloaded to supplementary files despite the document being extremely long. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (533 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
906a57d
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.